Statistical Dominance Algorithm
SDA performs the initial stage of edge detection or segmentation of digital grayscale images. The algorithm counts the number of pixels with a given relation to the central point of the neighborhood. The output image is a statistical result of the dominance of points over their neighborhoods and allows the classification of these points to be determined (peak, valley, and slope). Therefore, this solution allows the impact of noise or uneven illumination in image results to be reduced. [1], PDF
Main applications of the algorithm:
Small object detection (e.g. cell detection)
Segmentation
Edge detection
Image normalization
Other applications (e.g. car licence plates)
Download:
ImageJ plugin: SDA_.jar (M. Gumula)
script use: run("SDA ", "r=20 threshold=50 relationship=>= neighborhood=disc negative normalise");
Demo application SDA.exe (.Net 2.0), SDA4.exe (.Net 4.0),
The main idea
for (x = N; x < SX - N; x++)
for (y = N; y < SY - N; y++)
{
imgout[x,y] = 0;
for (i = -N; i <= N; i++)
for (j = -N; j <= N; j++)
if (i * i + j * j <= R * R)
if (imgin[x + i, y + j] >= imgin[x, y] + threshold)
imgout[x, y]++;
}
Small Object Detection
[2]
|
|
|
source
|
SDA (r=50, threshold=50)
|
SDA (r=50, threshold=50), binarization threshold=150
|
|
|
|
|
SDA (r=25, threshold=14)
|
plugin view
|
White Matter Hyperintensities dataset: wmh_plaques.zip [5], [6].
Segmentation
Segmentation of heart chambers (atria, ventricles) and valve leaflets on CT data
8-bit | SDA | settings | 16 bit (DICOM) -> PNG 16bit 1:1 | | SDA | settings |
| | |
| | |
| | |
| | |
Edge detection
|
|
|
|
|
|
|
|
|
Wood
|
grayscale
|
Red
|
Blue
|
SDA of grayscale
|
SDA of Red
|
SDA of Blue
|
SDA of grayscale
|
neighborhood:
|
|
|
|
horizontal
|
horizontal
|
horizontal
|
disc
|
SDA: r=20, threshold=0, neighborhood=horizontal
[4]
Image normalization
Normalization: Magnetic Resonance Imaging [3]
SDA parameters: r=50, threshold=0, neighborhood=disc
MRI normalization
Normalization: Corneal Endothelium Images [1]
|
|
|
|
|
source
|
normalized
|
smoothing
|
SDA
|
SDA
|
|
|
maximal filter 3x3
|
r=2, threshold=0
|
r=3, threshold=0
|
ImageJ script: corneal_normalization.ijm
youtube presentation (PL)
Enchancing the trabecular structure of bone on the X-ray images [7]
|
|
|
|
|
source
|
histogram equalisement
|
CLAHE
|
CLAHE+hist. equal.
|
SDA (r=50, thr=0, neg, disc)
|
|
|
maximal filter 3x3
|
r=2, threshold=0
|
r=3, threshold=0
|
Other applications
Examples:
- Car Licence Plates
Car Licence Plates
|
|
|
Car
|
Car - SDA, r=5.0, threshold=30
|
Car - SDA, r=5.0, threshold=120
|
References:
[1] Piorkowski A.: A Statistical Dominance Algorithm for Edge Detection and Segmentation of Medical Images. AISC vol. 471, Springer, 2016, pp. 3-14. PDF, bib.
[2] Nurzynska, K., Mikhalkin, A., Piorkowski, A.: CAS: Cell Annotation Software - Research on Neuronal Tissue Has Never Been so Transparent. Neuroinformatics, 2017, Vol. 15, Iss. 4, pp 365-382. Springer, PDF, bib.
[3] Obuchowicz, R., Urbanik, A., Piórkowski, A.: Novel Technique for Growth Plate Analysis Based on the Superposition of T1-and T2-weighted MR Imaging of Adolescent Wrists. Magnetic Resonance in Medical Sciences, 2020; 19(3): 259–267. PDF, bib.
[4] Fabijanska, A., Danek, M., Barniak, J., Piorkowski, A.: A Comparative Study of Image Enhancement Methods in Tree-Ring Analysis. In International Conference on Image Processing and Communications, Springer, AISC vol. 525, 2017, pp. 69-78. Springer
[5] Piorkowski A., Lasek J.: Evaluation of Local Thresholding Algorithms for Segmentation of White Matter Hyperintensities in Magnetic Resonance Images of the Brain. ICAI 2021. Springer, CCIS, vol. 1455, 2021, pp 331-345.
[6] Milewska, K., Obuchowicz, R., Piorkowski, A.: A preliminary approach to plaque detection in mri brain images. IEEE EMB ISC 2020. Springer, AISC, vol 1360, 2022, pp 94-105
[7] Kaminski, P., Nurzynska, K., Kwiecien, J., Obuchowicz, R., Piorkowski, A., Pociask, E., Stepien, A., Kociolek, M., Strzelecki, M., Augustyniak, P.: Sex Differentiation of Trabecular Bone Structure Based on Textural Analysis of Pelvic Radiographs. J. Clin. Med. 2024, 13, 1904. https://doi.org/10.3390/jcm13071904 PDF